Speakers
-
Theodoros Katsaounis (U Crete & FORTH, webpage)
Title: Mathematical Modelling, Simulations and Machine-Statistical Learning Techniques for Energy Yield Prediction of Solar Cells
Abstract: In this talk I will present a review of methods and techniques that we have been working lately concerning the mathematical modelling of solar cells of various architectures and the development of models and algorithms for accurate energy yield prediction of PV installations.
Bio: Theodoros Katsaounis received his BSc in Mathematics from Univ. of Crete, Greece in 1987 and in his PhD in 1994 in applied and computational mathematics from the Univ. of Tennessee, USA. He held various postdoc positions in Univ. of Crete, Greece, Univ. Tennessee, USA and Ecole Normale Superieure, France. In 2002 he joined as an assistant professor the Dept. Of Applied Mathematics of Univ. of Crete, Greece where he is currently a full professor and also a collaborative faculty member of Inst. of Applied & Computational Mathematics (IACM)-FORTH, Greece. His scientific expertise is in the area of Applied and Computational Mathematics and his research interests include the development, implementation, evaluation and analysis, of numerical methods for solving challenging problems arising from a broad range of applications such as fluid flows, water waves, solar cells.
-
Aristeidis Meletiou (Ministry of Digital Governance, LinkedIn)
Title: AI in the Energy Market: Navigating the Crossroads of Innovation, Disruption, and Risk
Abstract: In this presentation, we will discuss indicatively in which sectors of the Energy Market AI can be applied (for example, management, fraud detection, predictive maintenance, behavioral analysis, renewable energy integration) and what is happening in the global energy market in relation to the use of AI (percentages, investments, etc.) according to relevant surveys.
In addition, elements related to the "ethical concerns" arising from the use of AI (for example Transparency and Accountability, Bias Mitigation, Human Oversight and Control, Job displacement) will be mentioned, but also what is being done with respect to Security issues and Privacy.
Finally, it will be mentioned very briefly what is being done in Greece and the Public Administration regarding AI issues and what is planned to be done in the immediate future following the Digital Transformation Bible 2020-2025 (the arrival of AI on gov.gr, AI in management and processing of big data, AI in the security of technological infrastructures, combating tax evasion, fire detection, etc.).
Bio: Aristeidis Meletiou is the General Director of the General Directorate of Informatics and Communications Infrastructure at the Ministry of Digital Governance. He holds a Phd in Production and Management Engineering from the Technical University of Crete, and has previously served as the Director of Academic Affairs at the Technical University of Crete.
-
George Loizos (Regulatory Authority for Energy, Waste and Water, LinkedIn)
Title: Maths, Data and AI tools complementing the traditional Energy Regulator’s tasks.
Abstract: It will be discussed how maths, big data and AI tools may find application and complement the traditional Regulator’s tasks such as making regulatory rules, monitoring, dispute resolution etc. in supervising the competitive (retail/wholesale) and non-competitive (networks/infrastructure) energy markets.
Bio: Dr. George Loizos, PhD ('03), two M.Sc. ('95 & '98) and a B.Eng ('94) in Electrical and Electronic Engineering from Cardiff University is the Director of Strategy and International Affairs and in parallel the Head of Electricity Networks and New Technologies Unit in the Greek Regulatory Authority for Energy, Waste and Water.
With approximately 25 years active national and international presence in industry, academia, public sector, he is an experienced electricity systems regulator and energy researcher with skills in analysis, problem solving, administration, energy market, electricity networks regulation and energy efficiency.
He is an expert-evaluator of the European Commission and has participated in various technical assistance programs (Twinning/TAIEX) to neighboring countries of the European Union.
He has also a significant number of publications and currently teaches in two MSc Energy related courses.
He is married and has two daughters.
-
Vassilis Nikolopoulos (Avokado, LinkedIn)
Title: Artificial Intelligence in the energy flexibility market
Abstract: This presentation concerns the applications of artificial intelligence (AI) in the energy flexibility market, and the role of algorithms in smart energy storage.
Bio: Dr. Vassilis Nikolopoulos, is an active Deeptech Intrapreneur and Angel investor, leading the corporate Technology Transfer, Intrapreneurship & new ventures, R&D Innovation, AI strategy and Technology development. He is the co-founder & CTO of the deeptech technology spin off AVOKADO.
In the last 20 years, Vassilis has been working in applied research, technology transfer and innovation management procedures, focusing on the Big Data problems applied to Utilities and the digitalization of the Energy Sector. He co-founded the Deep tech startup Intelen, one of the most successful startups in the digital energy and utility analytics markets, having some big utilities as clients in Greece, Europe and USA. He has also worked for years in applied energy behavioral science, AI, data analytics, algorithms and the application of social networks to change human behaviors towards a more sustainable way of living.
He was also one of the two National Climate champions (Greece) of the British Council, taking part in the Global Youth Forum on Climate Finance 2010 in Shanghai. Being an active entrepreneur, applied researcher and passionate with technology futurology, he has cooperated with more than 40 utilities in the USA and Europe, dealing with customer engagement, customer analytics, AI/ML, energy management and deployment of new business models and digital services. He has global recognitions in top innovation and entrepreneurship contests (US Red herring, SVASE Silicon Valley, Siemens global smartgrid, OECD eco-innovation, CeBIT top cleantech, etc). He is the author of one book in Computer Networks, guest speaker in many conferences and futurology events (ie TedX, SAP Digital, Decentralized, PowerUP EIT, etc) and has more than 50 publications in conferences, journals and technology papers.
He is a valedictorian Electrical Engineer from Dundee University, Scotland with postgraduate studies at Imperial College, London School of Economics, Ecole Polytechnique (X) and a PhD from National Technical University of Athens. Also took various courses from HarvardX (Harvard University).”
-
Alexandros Saplaouras (NTUA, webpage)
Title: Predicting energy production using SDEs and machine learning
Abstract: Based on historical observations extracted from a wind farm and on the (deterministic) numerical weather prediction associated to the area where the farm is located in, we developd a methodology to forecast the short-term energy production of the farm.
The main tools in our mathematical arsenal are Ito's Stochastic Differential Equations and machine learning techniques.
Bio: Alexandros Saplaouras is the principal investigator of the H.F.R.I. project "Stability and Numerics for BSDEs under Uncertainty and Applications (START)" hosted by the National Technical University of Athens.
Previously, he was a Post-Doctoral Assistant Professor at the Department of Mathematics of the University of Michigan under the mentorship of Erhan Bayraktar.
He received his PhD in Mathematics from the Technische Universität Berlin under the supervision of Antonis Papapantoleon in 2017.
He was awarded the B. Alan Taylor Award for his outstanding teaching by the Department of Mathematics of the University of Michigan in 2019.
His main research interests lie in the areas of stochastic calculus with jumps, limit theorems for stochastic processes, their applications in mathematical finance and their numerical implementation.
His research work has been published in leading journals in mathematics and probability, Transactions of the American Mathematical Society and Electronic Journal of Probability.
-
Eleni Stai (NTUA, LinkedIn)
Title: Online Battery Control in Active Distribution Grids Using Lyapunov Optimization and Reinforcement Learning
Abstract: Energy storage in the form of batteries will likely play a crucial role in the operation of distribution grids that are characterized by a continuously growing integration of uncertain distributed energy resources. In this talk, we present computationally efficient real-time control schemes for batteries in active distribution grids with lookahead state-of-energy constraints. The goal is to follow a previously computed dispatch plan or to optimize a monetary cost from buying and selling power at the point of common coupling. However, the lookahead constraints render the battery decisions non-trivial. The common practice in literature to solve this problem is Model Predictive Control (MPC), which does not scale for large grids.
We first propose iterative Lyapunov Real-time Control (iLypRC), a fast online algorithm, which does not need forecasts. ILypRC is designed via Lyapunov optimization and requires only bounds on the uncertain quantities for each real-time interval. It efficiently accounts for grid losses, battery efficiency and grid constraints via iterative linearizations of the power flow equations. We compute a theoretical upper bound on the difference between the cost of iLypRC with the cost of an oracle. We show via numerical examples that iLypRC achieves a cost very close to that of MPC with good forecast, but iLypRC needs no forecast and has much lower run time complexity. In addition, when the MPC forecast is inaccurate, iLypRC outperforms MPC.
Second, we investigate a reinforcement learning approach based on the Deep Deterministic Policy Gradient (DDPG) algorithm. To satisfy the lookahead battery constraints we adapt the experience replay technique used in DDPG. To guarantee the satisfaction of the hard grid constraints, we introduce a safety layer that performs constrained optimization. We show that it can achieve costs close to MPC and Lyapunov, while reducing the computational time by multiple orders of magnitude.
Bio: Eleni Stai is an Assistant Professor at the School of Electrical and Computer Engineering at NTUA. She received the Diploma in Electrical and Computer Engineering from NTUA in 2009, the B.Sc. in Mathematics from the National and Kapodistrian University of Athens, in 2013, the M.Sc. in Applied Mathematical Sciences from NTUA in 2014 and the Ph.D. in Electrical Engineering from NTUA in 2015. From 2016 to 2020, she was a Postdoctoral researcher at the Laboratory for Communications & Applications at the ‘Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland. From 2020 to 2023, she was a Postdoctoral researcher at the Swiss Federal Institute of Technology (ETH) in Zurich, Switzerland. Her main research interests include stochastic and deterministic optimization techniques for networks, algorithms for communications networks, data analytics on complex networks and smart-grids control and applications.
